Fig. 3: Product map encoding and inversion.

A product map encoding, whereby each input variable xj is encoded into an individual qubit, and the snapshot used by the model corresponds to single-qubit measurements of the DLA basis elements. In this setting, the snapshot is trivial to invert and find the original data using the relation \({x}_{j}={\cos }^{-1}\left(2{{\mathbf{\gamma }}}^{(j)}\cdot {{\bf{e}}}_{{\rm{snap}}}\right)\).